Mohammad Mehdi Dehdar, Mustafa Jahangoshai Rezaee, Marzieh Zarinbal, Hamidreza Izadbakhsh,
Volume 29, Issue 4 (12-2018)
Abstract
Human-based quality control reduces the accuracy of this process. Also, the speed of decision making in some industries is very important. For removing these limitations in human-based quality control, in this paper, the design of an expert system for automatic and intelligent quality control is investigated. In fact, using an intelligent system, the accuracy in quality control is increased. It requires the knowledge of experts in quality control and design of expert systems based on the knowledge and information provided by human and equipment. For this purpose, Fuzzy Inference System (FIS) and Image Processing approach are integrated. In this expert system, the input information is the images of the products and the results of processing on images for quality control are as output. At first, they may be noisy images; the pre-processing is done and then a fuzzy system is used to be processed. In this fuzzy system, according to the images, the rules are designed to extract the specific features that are required. At second, after the required attributes are extracted, the control chart is used in terms of quality. Furthermore, the empirical case study of copper rods industry is presented to show the abilities of the proposed approach.
Amirhossein Masoumi, Rouzbeh Ghousi, Ahmad Makui,
Volume 33, Issue 3 (9-2022)
Abstract
Purpose: Non-cancerous prostate lesions such as prostate calcification, prostate enlargement, and prostate inflammation cause too many problems for men’s health. This research proposes a novel approach, a combination of image processing techniques and deep learning methods for classification and segmentation of the prostate in CT-scan images by considering the experienced physicians’ reports.
Methodology: Due to the various symptoms and nature of these lesions, a three-phases innovative approach has been implemented. In the first phase, using Mask R-CNN, in the second phase, considering the age of each patient and comparison with the standard size of the prostate gland, and finally, using the morphology features, the presence of three common non-cancerous lesions in the prostate gland has investigated.
Findings: A hierarchical multitask approach is introduced and the final amount of classification, localization, and segmentation loss is 1%, 1%, and 7%, respectively. Eventually, the overall loss ratio of the model is about 9%.
Originality: In this study, a medical assistant approach is introduced to increase diagnosis process accuracy and reduce error using a real dataset of abdominal and pelvics’ CT scans and the physicians’ reports for each image. A multi-tasks convolutional neural network; also presented to perform localization, classification, and segmentation of the prostate gland in CT scans at the same time.
